import numpy as np
import pickle
import cv2
import glob
import time
import os
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
from skimage.feature import hog
from sklearn.svm import LinearSVC
from skimage import data, exposure
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from scipy.ndimage.measurements import label
from ipywidgets import interact, interactive, fixed
from moviepy.editor import VideoFileClip
from IPython.display import HTML
%matplotlib inline
#print('The scikit-learn version is {}.'.format(sklearn.__version__))
car_images = glob.glob('vehicles/**/*.png')
noncar_images = glob.glob('non-vehicles/**/*.png')
print(len(car_images), len(noncar_images))
for i, fname in enumerate(car_images):
carImg = cv2.imread(fname)
carImg = cv2.cvtColor(carImg, cv2.COLOR_BGR2RGB)
for i, fname in enumerate(noncar_images):
noncarImg = cv2.imread(fname)
noncarImg = cv2.cvtColor(noncarImg, cv2.COLOR_BGR2RGB)
# Visualize undistortion
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))
ax1.set_title('Car Image', fontsize=30)
ax1.imshow(carImg)
ax2.set_title('Non Car Image', fontsize=30)
noncar_img = cv2.cvtColor(noncarImg, cv2.COLOR_BGR2RGB)
ax2.imshow(noncar_img)
car_images = glob.glob('vehicles/**/*.png')
noncar_images = glob.glob('non-vehicles/**/*.png')
cars = []
notcars = []
for image in car_images:
if 'image' in image:
cars.append(image)
for image in noncar_images:
if 'extra' in image:
notcars.append(image)
# Define a function to return some characteristics of the dataset
def data_look(car_list, notcar_list):
data_dict = {}
# Define a key in data_dict "n_cars" and store the number of car images
data_dict["n_cars"] = len(car_list)
# Define a key "n_notcars" and store the number of notcar images
data_dict["n_notcars"] = len(notcar_list)
# Read in a test image, either car or notcar
example_img = mpimg.imread(car_list[0])
# Define a key "image_shape" and store the test image shape 3-tuple
data_dict["image_shape"] = example_img.shape
# Define a key "data_type" and store the data type of the test image.
data_dict["data_type"] = example_img.dtype
# Return data_dict
return data_dict
data_info = data_look(cars, notcars)
print('Your function returned a count of',
data_info["n_cars"], ' cars and',
data_info["n_notcars"], ' non-cars')
print('of size: ',data_info["image_shape"], ' and data type:',
data_info["data_type"])
# Just for fun choose random car / not-car indices and plot example images
car_ind = np.random.randint(0, len(cars))
notcar_ind = np.random.randint(0, len(notcars))
# Read in car / not-car images
car_image = mpimg.imread(cars[car_ind])
notcar_image = mpimg.imread(notcars[notcar_ind])
# Plot the examples
fig = plt.figure()
plt.subplot(121)
plt.imshow(car_image)
plt.title('Example Car Image')
plt.subplot(122)
plt.imshow(notcar_image)
plt.title('Example Not-car Image')
(optional) global image normalization
computing the gradient image in row and col
computing gradient histograms
normalizing across blocks
flattening into a feature vector
# Define a function to return HOG features and visualization
def get_hog_features(img,
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True):
if vis == True:
features, hog_image = hog(img,
orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=False,
visualise=True,
feature_vector=True)
return features, hog_image
else:
features = hog(img,
orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=False,
visualise=False,
feature_vector=feature_vec)
return features
# Generate a random index to look at a car image
ind = np.random.randint(0, len(cars))
n_ind = np.random.randint(0, len(notcars))
# Read in the image
image = mpimg.imread(cars[ind])
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
n_image = mpimg.imread(notcars[n_ind])
n_gray = cv2.cvtColor(n_image, cv2.COLOR_RGB2GRAY)
# Define HOG parameters
orient = 11
pix_per_cell = 8
cell_per_block = 2
# Call our function with vis=True to see an image output
features, hog_image = get_hog_features(gray,
orient,
pix_per_cell,
cell_per_block,
vis=True,
feature_vec=True)
# Call our function with vis=True to see an image output
n_features, n_hog_image = get_hog_features(n_gray,
orient,
pix_per_cell,
cell_per_block,
vis=True,
feature_vec=True)
# Plot the examples
fig = plt.figure()
plt.subplot(121)
plt.imshow(image, cmap='gray')
plt.title('Example Car Image')
plt.subplot(122)
plt.imshow(hog_image, cmap='gray')
plt.title('HOG Visualization')
# Plot the examples
fig = plt.figure()
plt.subplot(121)
plt.imshow(n_image, cmap='gray')
plt.title('Example Non Car Image')
plt.subplot(122)
plt.imshow(n_hog_image, cmap='gray')
plt.title('HOG Visualization')
# Define a function to compute binned color features
def bin_spatial(img, size=(32, 32)):
# Use cv2.resize().ravel() to create the feature vector
features = cv2.resize(img, size).ravel()
# Return the feature vector
return features
# Define a function to compute color histogram features
def color_hist(img, nbins=32, bins_range=(0, 256)):
# Compute the histogram of the color channels separately
channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)
channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)
channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))
# Return the individual histograms, bin_centers and feature vector
return hist_features
# Define a function to extract features from a list of images
# Have this function call bin_spatial() and color_hist()
def extract_features(imgs, color_space='RGB', spatial_size=(32, 32),
hist_bins=32, orient=11,
pix_per_cell=8, cell_per_block=2, hog_channel=0,
spatial_feat=True, hist_feat=True, hog_feat=True):
# Create a list to append feature vectors to
features = []
# Iterate through the list of images
for file in imgs:
file_features = []
# Read in each one by one
image = mpimg.imread(file)
# apply color conversion if other than 'RGB'
if color_space != 'RGB':
if color_space == 'HSV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YCrCb)
else: feature_image = np.copy(image)
if spatial_feat == True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
file_features.append(spatial_features)
if hist_feat == True:
# Apply color_hist()
hist_features = color_hist(feature_image, nbins=hist_bins)
file_features.append(hist_features)
if hog_feat == True:
# Call get_hog_features() with vis=False, feature_vec=True
if hog_channel == 'ALL':
hog_features = []
for channel in range(feature_image.shape[2]):
hog_features.append(get_hog_features(feature_image[:,:,channel],
orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=True))
hog_features = np.ravel(hog_features)
else:
hog_features = get_hog_features(feature_image[:,:,hog_channel], orient,
pix_per_cell, cell_per_block, vis=False, feature_vec=True)
# Append the new feature vector to the features list
file_features.append(hog_features)
features.append(np.concatenate(file_features))
# Return list of feature vectors
return features
# Reduce the sample size because
# The quiz evaluator times out after 13s of CPU time
sample_size = 500
cars = cars[0:sample_size]
notcars = notcars[0:sample_size]
color_space = 'RGB' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11 # HOG orientations
pix_per_cell = 8 # HOG pixels per cell
cell_per_block = 2 # HOG cells per block
hog_channel = 0 # Can be 0, 1, 2, or "ALL"
spatial_size = (32, 32) # Spatial binning dimensions
hist_bins = 32 # Number of histogram bins
spatial_feat = True # Spatial features on or off
hist_feat = True # Histogram features on or off
hog_feat = True # HOG features on or off
y_start_stop = [None, None] # Min and max in y to search in slide_window()
car_features = extract_features(cars, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
notcar_features = extract_features(notcars, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
if len(car_features) > 0:
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
car_ind = np.random.randint(0, len(cars))
# Plot an example of raw and scaled features
fig = plt.figure(figsize=(12,4))
plt.subplot(131)
plt.imshow(mpimg.imread(cars[car_ind]))
plt.title('Original Image')
plt.subplot(132)
plt.plot(X[car_ind])
plt.title('Raw Features')
plt.subplot(133)
plt.plot(scaled_X[car_ind])
plt.title('Normalized Features')
fig.tight_layout()
else:
print('Your function only returns empty feature vectors...')
Training Set
Test Set
spatial = 32
histbin = 32
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using spatial binning of:',spatial,
'and', histbin,'histogram bins')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
# Check the training time for the SVC
t = time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
n_predict = 10
print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))
print('For these',n_predict, 'labels: ', y_test[0:n_predict])
t2 = time.time()
print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')
colorspace = 'LUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11
pix_per_cell = 8
cell_per_block = 2
hog_channel = 0 # Can be 0, 1, 2, or "ALL"
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using:',orient,'orientations',pix_per_cell,
'pixels per cell and', cell_per_block,'cells per block')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
# Check the training time for the SVC
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
n_predict = 10
print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))
print('For these',n_predict, 'labels: ', y_test[0:n_predict])
t2 = time.time()
print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')
# Here is the draw_boxes function
def draw_boxes(img, bboxes, color=(0, 0, 255), thick=6):
# Make a copy of the image
imcopy = np.copy(img)
random_color = False
# Iterate through the bounding boxes
for bbox in bboxes:
if color == 'random' or random_color:
color = (np.random.randint(0,255), np.random.randint(0,255), np.random.randint(0,255))
random_color = True
# Draw a rectangle given bbox coordinates
cv2.rectangle(imcopy, bbox[0], bbox[1], color, thick)
# Return the image copy with boxes drawn
return imcopy
def slide_window(img, x_start_stop=[None, None], y_start_stop=[None, None],
xy_window=(64, 64), xy_overlap=(0.5, 0.5)):
# If x and/or y start/stop positions not defined, set to image size
if x_start_stop[0] == None:
x_start_stop[0] = 0
if x_start_stop[1] == None:
x_start_stop[1] = img.shape[1]
if y_start_stop[0] == None:
y_start_stop[0] = 0
if y_start_stop[1] == None:
y_start_stop[1] = img.shape[0]
# Compute the span of the region to be searched
xspan = x_start_stop[1] - x_start_stop[0]
yspan = y_start_stop[1] - y_start_stop[0]
# Compute the number of pixels per step in x/y
nx_pix_per_step = np.int(xy_window[0]*(1 - xy_overlap[0]))
ny_pix_per_step = np.int(xy_window[1]*(1 - xy_overlap[1]))
# Compute the number of windows in x/y
nx_buffer = np.int(xy_window[0]*(xy_overlap[0]))
ny_buffer = np.int(xy_window[1]*(xy_overlap[1]))
nx_windows = np.int((xspan-nx_buffer)/nx_pix_per_step)
ny_windows = np.int((yspan-ny_buffer)/ny_pix_per_step)
# Initialize a list to append window positions to
window_list = []
# Loop through finding x and y window positions
# Note: you could vectorize this step, but in practice
# you'll be considering windows one by one with your
# classifier, so looping makes sense
for ys in range(ny_windows):
for xs in range(nx_windows):
# Calculate window position
startx = xs*nx_pix_per_step + x_start_stop[0]
endx = startx + xy_window[0]
starty = ys*ny_pix_per_step + y_start_stop[0]
endy = starty + xy_window[1]
# Append window position to list
window_list.append(((startx, starty), (endx, endy)))
# Return the list of windows
return window_list
image = mpimg.imread('./test_images/test1.jpg')
windows = slide_window(image, x_start_stop=[None, None], y_start_stop=[None, None],
xy_window=(96, 96), xy_overlap=(0.5, 0.5))
window_img = draw_boxes(image, windows, color=(0, 0, 255), thick=6)
plt.imshow(window_img)
# Define a function to compute color histogram features
# NEED TO CHANGE bins_range if reading .png files with mpimg!
def color_hist(img, nbins=32, bins_range=(0, 256)):
# Compute the histogram of the color channels separately
channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)
channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)
channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))
# Return the individual histograms, bin_centers and feature vector
return hist_features
# Define a function to extract features from a single image window
# This function is very similar to extract_features()
# just for a single image rather than list of images
def single_img_features(img, color_space='RGB', spatial_size=(32, 32),
hist_bins=32, orient=11,
pix_per_cell=8, cell_per_block=2, hog_channel=0,
spatial_feat=True, hist_feat=True, hog_feat=True):
#1) Define an empty list to receive features
img_features = []
#2) Apply color conversion if other than 'RGB'
if color_space != 'RGB':
if color_space == 'HSV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
else: feature_image = np.copy(img)
#3) Compute spatial features if flag is set
if spatial_feat == True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
#4) Append features to list
img_features.append(spatial_features)
#5) Compute histogram features if flag is set
if hist_feat == True:
hist_features = color_hist(feature_image, nbins=hist_bins)
#6) Append features to list
img_features.append(hist_features)
#7) Compute HOG features if flag is set
if hog_feat == True:
if hog_channel == 'ALL':
hog_features = []
for channel in range(feature_image.shape[2]):
hog_features.extend(get_hog_features(feature_image[:,:,channel],
orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=True))
else:
hog_features = get_hog_features(feature_image[:,:,hog_channel], orient,
pix_per_cell, cell_per_block, vis=False, feature_vec=True)
#8) Append features to list
img_features.append(hog_features)
#9) Return concatenated array of features
return np.concatenate(img_features)
# Define a function you will pass an image
# and the list of windows to be searched (output of slide_windows())
def search_windows(img, windows, clf, scaler, color_space='RGB',
spatial_size=(32, 32), hist_bins=32,
hist_range=(0, 256), orient=11,
pix_per_cell=8, cell_per_block=2,
hog_channel=0, spatial_feat=True,
hist_feat=True, hog_feat=True):
#1) Create an empty list to receive positive detection windows
on_windows = []
#2) Iterate over all windows in the list
for window in windows:
#3) Extract the test window from original image
test_img = cv2.resize(img[window[0][1]:window[1][1], window[0][0]:window[1][0]], (64, 64))
#4) Extract features for that window using single_img_features()
features = single_img_features(test_img, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
#5) Scale extracted features to be fed to classifier
test_features = scaler.transform(np.array(features).reshape(1, -1))
#6) Predict using your classifier
prediction = clf.predict(test_features)
#7) If positive (prediction == 1) then save the window
if prediction == 1:
on_windows.append(window)
#8) Return windows for positive detections
return on_windows
# Reduce the sample size because
# The quiz evaluator times out after 13s of CPU time
sample_size = 500
cars = cars[0:sample_size]
notcars = notcars[0:sample_size]
color_space = 'RGB' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11 # HOG orientations
pix_per_cell = 8 # HOG pixels per cell
cell_per_block = 2 # HOG cells per block
hog_channel = "ALL" # Can be 0, 1, 2, or "ALL"
spatial_size = (32, 32) # Spatial binning dimensions
hist_bins = 32 # Number of histogram bins
spatial_feat = True # Spatial features on or off
hist_feat = True # Histogram features on or off
hog_feat = True # HOG features on or off
y_start_stop = [None, None] # Min and max in y to search in slide_window()
car_features = extract_features(cars, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
notcar_features = extract_features(notcars, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using:',orient,'orientations',pix_per_cell,
'pixels per cell and', cell_per_block,'cells per block')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
# Check the training time for the SVC
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
image = mpimg.imread('./test_images/test1.jpg')
draw_image = np.copy(image)
# Uncomment the following line if you extracted training
# data from .png images (scaled 0 to 1 by mpimg) and the
# image you are searching is a .jpg (scaled 0 to 255)
#image = image.astype(np.float32)/255
windows = slide_window(image, x_start_stop=[None, None], y_start_stop=y_start_stop,
xy_window=(128, 128), xy_overlap=(0.5, 0.5))
hot_windows = search_windows(image, windows, svc, X_scaler, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
window_img = draw_boxes(draw_image, hot_windows, color=(0, 0, 255), thick=6)
plt.imshow(window_img)
# Save the SVC result for later use
svc_pickle = {}
svc_pickle["svc"] = svc
svc_pickle["scaler"] = X_scaler
svc_pickle["orient"] = orient
svc_pickle["pix_per_cell"] = pix_per_cell
svc_pickle["cell_per_block"] = cell_per_block
svc_pickle["spatial_size"] = (32,32)
svc_pickle["hist_bins"] = 32
svc_pickle["hog_channel"] = hog_channel
print(X_scaler)
print(orient)
print(pix_per_cell)
print(cell_per_block)
print(spatial_size)
print(hist_bins)
print(hog_channel)
pickle.dump( svc_pickle, open( "./svc_pickle.p", "wb" ) )
dist_pickle = pickle.load( open("svc_pickle.p", "rb" ) )
svc = dist_pickle["svc"]
X_scaler = dist_pickle["scaler"]
orient = dist_pickle["orient"]
pix_per_cell = dist_pickle["pix_per_cell"]
cell_per_block = dist_pickle["cell_per_block"]
spatial_size = dist_pickle["spatial_size"]
hist_bins = dist_pickle["hist_bins"]
def convert_color(img, conv='RGB2YCrCb'):
if conv == 'RGB2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
if conv == 'BGR2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_BGR2YCrCb)
if conv == 'RGB2LUV':
return cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
# Define a single function that can extract features using hog sub-sampling and make predictions
def find_cars(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size,
hist_bins, show_all_rectangles=False):
# array of rectangles where cars were detected
rectangles = []
draw_img = np.copy(img)
img = img.astype(np.float32)/255
img_tosearch = img[ystart:ystop,:,:]
ctrans_tosearch = convert_color(img_tosearch, conv='RGB2YCrCb')
if scale != 1:
imshape = ctrans_tosearch.shape
ctrans_tosearch = cv2.resize(ctrans_tosearch, (np.int(imshape[1]/scale), np.int(imshape[0]/scale)))
ch1 = ctrans_tosearch[:,:,0]
ch2 = ctrans_tosearch[:,:,1]
ch3 = ctrans_tosearch[:,:,2]
# Define blocks and steps as above
nxblocks = (ch1.shape[1] // pix_per_cell)+1 #-1
nyblocks = (ch1.shape[0] // pix_per_cell)+1 #-1
nfeat_per_block = orient*cell_per_block**2
# 64 was the orginal sampling rate, with 8 cells and 8 pix per cell
window = 64
nblocks_per_window = (window // pix_per_cell)-1
cells_per_step = 2 # Instead of overlap, define how many cells to step
nxsteps = (nxblocks - nblocks_per_window) // cells_per_step
nysteps = (nyblocks - nblocks_per_window) // cells_per_step
# Compute individual channel HOG features for the entire image
hog1 = get_hog_features(ch1, orient, pix_per_cell, cell_per_block, feature_vec=False)
hog2 = get_hog_features(ch2, orient, pix_per_cell, cell_per_block, feature_vec=False)
hog3 = get_hog_features(ch3, orient, pix_per_cell, cell_per_block, feature_vec=False)
for xb in range(nxsteps):
for yb in range(nysteps):
ypos = yb*cells_per_step
xpos = xb*cells_per_step
# Extract HOG for this patch
hog_feat1 = hog1[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel()
hog_feat2 = hog2[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel()
hog_feat3 = hog3[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel()
hog_features = np.hstack((hog_feat1, hog_feat2, hog_feat3))
xleft = xpos*pix_per_cell
ytop = ypos*pix_per_cell
# Extract the image patch
subimg = cv2.resize(ctrans_tosearch[ytop:ytop+window, xleft:xleft+window], (64,64))
# Get color features
spatial_features = bin_spatial(subimg, size=spatial_size)
hist_features = color_hist(subimg, nbins=hist_bins)
# Scale features and make a prediction
test_features = X_scaler.transform(np.hstack((spatial_features, hist_features,
hog_features)).reshape(1, -1))
#test_features = X_scaler.transform(np.hstack((shape_feat, hist_feat)).reshape(1, -1))
test_prediction = svc.predict(test_features)
if test_prediction == 1:
xbox_left = np.int(xleft*scale)
ytop_draw = np.int(ytop*scale)
win_draw = np.int(window*scale)
cv2.rectangle(draw_img,(xbox_left, ytop_draw+ystart),
(xbox_left+win_draw,ytop_draw+win_draw+ystart),(0,0,255),6)
rectangles.append(((xbox_left, ytop_draw+ystart),(xbox_left+win_draw,ytop_draw+win_draw+ystart)))
return rectangles
test_img = mpimg.imread('./test_images/test1.jpg')
ystart = 400
ystop = 656
scale = 1.5
colorspace = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11
pix_per_cell = 8
cell_per_block = 2
hog_channel = 'ALL' # Can be 0, 1, 2, or "ALL"
rectangles = find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None)
print(len(rectangles), 'rectangles found in image')
test_img_rects = draw_boxes(test_img, rectangles)
plt.figure(figsize=(10,10))
plt.imshow(test_img_rects)
test_img = mpimg.imread('./test_images/test1.jpg')
rects = []
ystart = 400
ystop = 464
scale = 1.0
rects.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, show_all_rectangles=True))
ystart = 416
ystop = 480
scale = 1.0
rects.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, show_all_rectangles=True))
rectangles = [item for sublist in rects for item in sublist]
test_img_rects = draw_boxes(test_img, rectangles, color='random', thick=2)
plt.figure(figsize=(10,10))
plt.imshow(test_img_rects)
print('Number of boxes: ', len(rectangles))
test_img = mpimg.imread('./test_images/test1.jpg')
rects = []
ystart = 400
ystop = 496
scale = 1.5
rects.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, show_all_rectangles=True))
ystart = 432
ystop = 528
scale = 1.5
rects.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, show_all_rectangles=True))
rectangles = [item for sublist in rects for item in sublist]
test_img_rects = draw_boxes(test_img, rectangles, color='random', thick=2)
plt.figure(figsize=(10,10))
plt.imshow(test_img_rects)
print('Number of boxes: ', len(rectangles))
test_img = mpimg.imread('./test_images/test1.jpg')
rects = []
ystart = 400
ystop = 528
scale = 2.0
rects.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, show_all_rectangles=True))
ystart = 432
ystop = 560
scale = 2.0
rects.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, show_all_rectangles=True))
rectangles = [item for sublist in rects for item in sublist]
test_img_rects = draw_boxes(test_img, rectangles, color='random', thick=2)
plt.figure(figsize=(10,10))
plt.imshow(test_img_rects)
print('Number of boxes: ', len(rectangles))
test_img = mpimg.imread('./test_images/test1.jpg')
rectangles = []
colorspace = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11
pix_per_cell = 8
cell_per_block = 2
hog_channel = 'ALL' # Can be 0, 1, 2, or "ALL"
ystart = 400
ystop = 464
scale = 1.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 416
ystop = 480
scale = 1.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 400
ystop = 496
scale = 1.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 432
ystop = 528
scale = 1.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 400
ystop = 528
scale = 2.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 432
ystop = 560
scale = 2.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 400
ystop = 596
scale = 3.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 464
ystop = 660
scale = 3.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
# apparently this is the best way to flatten a list of lists
rectangles = [item for sublist in rectangles for item in sublist]
test_img_rects = draw_boxes(test_img, rectangles, color='random', thick=2)
plt.figure(figsize=(10,10))
plt.imshow(test_img_rects)
def add_heat(heatmap, bbox_list):
# Iterate through list of bboxes
for box in bbox_list:
# Add += 1 for all pixels inside each bbox
# Assuming each "box" takes the form ((x1, y1), (x2, y2))
heatmap[box[0][1]:box[1][1], box[0][0]:box[1][0]] += 1
# Return updated heatmap
return heatmap# Iterate through list of bboxes
# Test out the heatmap
heatmap_img = np.zeros_like(test_img[:,:,0])
heatmap_img = add_heat(heatmap_img, rectangles)
plt.figure(figsize=(10,10))
plt.imshow(heatmap_img, cmap='hot')
def apply_threshold(heatmap, threshold):
# Zero out pixels below the threshold
heatmap[heatmap <= threshold] = 0
# Return thresholded map
return heatmap
heatmap_img = apply_threshold(heatmap_img, 1)
plt.figure(figsize=(10,10))
plt.imshow(heatmap_img, cmap='hot')
labels = label(heatmap_img)
plt.figure(figsize=(10,10))
plt.imshow(labels[0], cmap='gray')
print(labels[1], 'cars found')
def draw_labeled_bboxes(img, labels):
# Iterate through all detected cars
rects = []
for car_number in range(1, labels[1]+1):
# Find pixels with each car_number label value
nonzero = (labels[0] == car_number).nonzero()
# Identify x and y values of those pixels
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Define a bounding box based on min/max x and y
bbox = ((np.min(nonzerox), np.min(nonzeroy)), (np.max(nonzerox), np.max(nonzeroy)))
rects.append(bbox)
# Draw the box on the image
cv2.rectangle(img, bbox[0], bbox[1], (0,0,255), 6)
# Return the image and final rectangles
return img, rects
# Draw bounding boxes on a copy of the image
draw_img, rect = draw_labeled_bboxes(np.copy(test_img), labels)
# Display the image
plt.figure(figsize=(10,10))
plt.imshow(draw_img)
def process_frame(img):
rectangles = []
colorspace = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11
pix_per_cell = 8
cell_per_block = 2
hog_channel = 'ALL' # Can be 0, 1, 2, or "ALL"
ystart = 400
ystop = 464
scale = 1.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 416
ystop = 480
scale = 1.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 400
ystop = 496
scale = 1.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 432
ystop = 528
scale = 1.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 400
ystop = 528
scale = 2.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 432
ystop = 560
scale = 2.0
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 400
ystop = 596
scale = 3.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
ystart = 464
ystop = 660
scale = 3.5
rectangles.append(find_cars(test_img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell,
cell_per_block, spatial_size, hist_bins, None))
rectangles = [item for sublist in rectangles for item in sublist]
heatmap_img = np.zeros_like(img[:,:,0])
heatmap_img = add_heat(heatmap_img, rectangles)
heatmap_img = apply_threshold(heatmap_img, 1)
labels = label(heatmap_img)
draw_img, rects = draw_labeled_bboxes(np.copy(img), labels)
return draw_img
test_images = glob.glob('./test_images/test*.jpg')
fig, axs = plt.subplots(3, 2, figsize=(16,14))
fig.subplots_adjust(hspace = .004, wspace=.002)
axs = axs.ravel()
for i, im in enumerate(test_images):
axs[i].imshow(process_frame(mpimg.imread(im)))
axs[i].axis('off')
test_out_file = 'test_video_out.mp4'
clip_test = VideoFileClip('test_video.mp4')
clip_test_out = clip_test.fl_image(process_frame)
%time clip_test_out.write_videofile(test_out_file, audio=False)